In the past, the construction industry has been slow to adopt new technology. There has been a rapid expansion of technologies, often referred to as Industry 4.0, to aid in the use of automation. One challenge paralleling these new technologies is implementing how a robot interprets design information, specifically information from a Building Information Model (BIM). This paper presents a method for identifying and transforming information from BIM to support robotic material placement on the construction site. This research will include a review of what information can be directly extracted from the model and what must be supplemented to the model for the robot to perform defined tasks within a construction site. The construction sites’ dynamic nature poses multiple challenges that must be addressed for the information extracted from a model to be used by a robot in daily construction operations. This research also identifies barriers and limitations based upon current practice, such as different levels of development or model content as well as needed precision within the information provided for a mobile robot to complete a defined task.
more »
« less
Computer Vision-Based Geometry Mapping and Matching of Building Elements for Construction Robotic Applications
Robotic automation of construction tasks is a growing area of research. For robots to successfully operate in a construction environment, sensing technology must be developed which allows for accurate detection of site geometry in a wide range of conditions. Much of the existing body of research on computer vision systems for construction automation focuses on pick-and-place operations such as stacking blocks or placing masonry elements. Very little research has focused on framing and related tasks. The research presented here aims to address this gap by designing and implementing computer vision algorithms for detection and measurement of building framing elements and testing those algorithms using realistic framing structures. These algorithms allow for a stationary RGB-D camera to accurately detect, identify, and measure the geometry of framing elements in a construction environment and match the detected geometry to provided building information modeling (BIM) data. The algorithms reduce identified framing elements to a simplified 3D geometric model, which allows for robust and accurate measurement and comparison with BIM data. This data can then be used to direct operations of construction robotic systems or other machines/equipment. The proposed algorithms were tested in a laboratory setting using an Intel RealSense D455 RGB-D camera, and initial results indicate that the system is capable of measuring the geometry of timber-frame structures with accuracy on the order of a few centimeters.
more »
« less
- Award ID(s):
- 1827733
- NSF-PAR ID:
- 10324509
- Date Published:
- Journal Name:
- Construction Research Congress 2022
- Page Range / eLocation ID:
- 541 to 549
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Desjardin, S. and (Ed.)Building Information Modeling (BIM) is a critical data source for constructing new structures depicting the inner workings of the systems and components in detail. However, current modeling practices are based on traditional construction methods, resulting in insufficient details within the BIM model to support robotic construction for many building systems. The model’s level of development (LOD) needs to be increased to facilitate the changes in data requirements. One method that allows for increased LOD is computational modeling; however, many factors can influence the process. Therefore, this study investigates challenges for implementation to increase the LOD for building to enable robotic construction. Dynamo is used as the computational modeling software in conjunction with Autodesk Revit to accomplish this. A process was created to place various components, such as concrete masonry units (CMUs), in their final design location and extract information utilizing these platforms for masonry construction. However, challenges were met during this process, including material naming conventions, tolerance/specification inputs, wall openings/lintels, and component/material libraries. The challenges presented during the implementation of the Dynamo mirror what the literature shows for supporting technological infrastructure BIM and mobile robot construction. To accomplish this research, an extensive literature review was completed, along with documentation of challenges during the development and implementation of the script.more » « less
-
Evolution has honed predatory skills in the natural world where localizing and intercepting fast-moving prey is required. The current generation of robotic systems mimics these biological systems using deep learning. High-speed processing of the camera frames using convolutional neural networks (CNN) (frame pipeline) on such constrained aerial edge-robots gets resource-limited. Adding more compute resources also eventually limits the throughput at the frame rate of the camera as frame-only traditional systems fail to capture the detailed temporal dynamics of the environment. Bio-inspired event cameras and spiking neural networks (SNN) provide an asynchronous sensor-processor pair (event pipeline) capturing the continuous temporal details of the scene for high-speed but lag in terms of accuracy. In this work, we propose a target localization system combining event-camera and SNN-based high-speed target estimation and frame-based camera and CNN-driven reliable object detection by fusing complementary spatio-temporal prowess of event and frame pipelines. One of our main contributions involves the design of an SNN filter that borrows from the neural mechanism for ego-motion cancelation in houseflies. It fuses the vestibular sensors with the vision to cancel the activity corresponding to the predator's self-motion. We also integrate the neuro-inspired multi-pipeline processing with task-optimized multi-neuronal pathway structure in primates and insects. The system is validated to outperform CNN-only processing using prey-predator drone simulations in realistic 3D virtual environments. The system is then demonstrated in a real-world multi-drone set-up with emulated event data. Subsequently, we use recorded actual sensory data from multi-camera and inertial measurement unit (IMU) assembly to show desired working while tolerating the realistic noise in vision and IMU sensors. We analyze the design space to identify optimal parameters for spiking neurons, CNN models, and for checking their effect on the performance metrics of the fused system. Finally, we map the throughput controlling SNN and fusion network on edge-compatible Zynq-7000 FPGA to show a potential 264 outputs per second even at constrained resource availability. This work may open new research directions by coupling multiple sensing and processing modalities inspired by discoveries in neuroscience to break fundamental trade-offs in frame-based computer vision 1 .more » « less
-
The adoption of robotics into the construction industry has been progressing slower than in the manufacturing and industrial sectors. Current shortfalls in skilled labor, productivity trends, and ongoing safety challenges point to the need for a drastic shift toward adopting robotics. Addressing these shortfalls would be a necessary component of the shift toward industrializing the construction industry. Despite this lag in technology adoption, the interest and development of robotic technology targeting the construction industry has grown in recent years and is ranging from the use of drones for tracking to advances in offsite fabrication. However, the integration into fundamental site construction necessitates reconsidering the information technology infrastructure needed to support detailed task execution information needs in the change from craft labor to robotic operations. This research presents the identification and mapping of the Information Technology (IT) system architecture required to support building information modeling (BIM) to robotic construction. Combining elements of BIM architecture and information exchanges with the needed construction task decomposition is required. These elements are mapped to the robotic system elements vital for mobile robotic operations. In addition to defining the functions and integration required to support the BIM to robotic Construction Workflow, shortcomings in existing infrastructure, notably regarding the ability to decompose construction fabrication and assembly means and methods, are defined.more » « less
-
The adoption of robotics into the construction industry has been much slower than in manufacturing and industrial sectors. Current shortfalls in skilled labor, productivity trends, and ongoing safety challenges point to the need for a drastic shift toward the adoption of robotics as a component of a shift toward industrialized construction. Despite this lag, the interest and development of robotic technology targeting construction has grown in recent years, ranging from the use of drones for tracking to use in offsite fabrication. However, the integration into fundamental site construction requires reconsideration of the information technology infrastructure needed to support detailed task execution information needs in the transition from craft labor to robotic operations. This research presents the identification and mapping of the IT System Architecture required to support BIM to Robotic Construction. Combining elements of the Building Information Modeling architecture and information exchanges with the needed construction task decomposition is required. These elements are mapped to the robotic system elements required for mobile robotic operations. In addition to defining the functions and integration required to support the BIM to Robotic Construction Workflow, shortcomings in existing infrastructure, notably regarding the ability to decompose construction fabrication and assembly means and methods are defined.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1061/9780784483961.057
